nateraw/mixtral-8x7b-32kseqlen 🔢📝 → 📝

▶️ 15.1K runs 📅 Dec 2023 ⚙️ Cog 0.9.0-beta10 🔗 GitHub
code-generation long-context text-generation text-translation

About

The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

Example Output

Prompt:

"

Here are the top 10 useful Hindi phrases for your upcoming trip to India:

1.

"

Output

नमस्ते (Namaste): This is the most common greeting in India and is used to say “hello” or “goodbye.” It is a respectful way to greet someone and can be used with anyone, regardless of age or gender.
2. धन्यवाद (Dhanyavaad): This is the Hindi word for “thank you” and is used to express gratitude. It is important to use this phrase when someone does something for you or when you receive a gift or favor.
3. क्या हाल है? (Kya Haal Hai?): This phrase means “how are you?” and is used to ask someone about their well-being. It is a polite way to start a conversation and can be used with anyone, regardless of age or gender.
4. मैं बहुत अच्छा हूँ (Main Bahaaut Acha Hoon): This phrase means “I am very good” and is used as a response to the question “how are you?” It is a polite way to let someone know that you are doing well.
5. क्या आप हिंदी बोलते हैं? (Kya Aap Hindi Bolte Hain?): This phrase means “do you speak Hindi?” and is used to ask someone if they speak the language. It is a polite way to start a conversation and can be used with anyone, regardless of age or gender.
6. क्या आप इंग्लिश बोलते हैं? (Kya Aap English Bolte Hain?): This phrase means “do you speak English?” and is used to ask someone if they speak the language. It is a polite way to start a conversation and can be used with anyone, regardless of age or gender.
7. क्या आप कैसे पहुँचे? (Kya Aap Kaise Pahunche?): This phrase means “how did you get here?” and is used to ask someone how they arrived at a particular location. It is a polite way to start a conversation and can be used with anyone, regardless of age or gender.

Performance Metrics

38.19s Prediction Time
178.54s Total Time
All Input Parameters
{
  "top_p": 0.9,
  "prompt": "Here are the top 10 useful Hindi phrases for your upcoming trip to India:\n\n1. ",
  "temperature": 0.6,
  "max_new_tokens": 512
}
Input Parameters
top_p Type: numberDefault: 0.9
A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
prompt (required) Type: string
temperature Type: numberDefault: 0.6
The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 512
The maximum number of tokens the model should generate as output.
Output Schema

Output

Type: string

Example Execution Logs
generation took 38.182s
Version Details
Version ID
defd13a450b135eab8f24e23f9659c71eed07b8de1b0dde9503a6e8a961d5510
Version Created
December 9, 2023
Run on Replicate →